This forum is disabled, please visit https://forum.opencv.org
 | 1 | initial version |
I think you need to train a new classifier.In the data base of positives samples you will add side faces. If you want to learn how to construct you own data base you can read this:
Theory: http://www.vision.caltech.edu/html-files/EE148-2005-Spring/pprs/viola04ijcv.pdf https://en.wikipedia.org/wiki/Haar-like_features https://en.wikipedia.org/wiki/Viola%E2%80%93Jones_object_detection_framework https://en.wikipedia.org/wiki/AdaBoost https://youtu.be/_QZLbR67fUU?list=PLg9RM7qfVLprS4Ww9W5RfSruPkvSXOipW
Practical case: http://www.memememememememe.me/training-haar-cascades/
